/**
* Emit code that kills pixels whose X and Y coordinates are outside the
* boundary of the rectangle defined by the push constants (dst_x0, dst_y0,
* dst_x1, dst_y1).
*/
void
brw_blorp_eu_emitter::emit_kill_if_outside_rect(const struct brw_reg &x,
const struct brw_reg &y,
const struct brw_reg &dst_x0,
const struct brw_reg &dst_x1,
const struct brw_reg &dst_y0,
const struct brw_reg &dst_y1)
{
struct brw_reg f0 = brw_flag_reg(0, 0);
struct brw_reg g1 = retype(brw_vec1_grf(1, 7), BRW_REGISTER_TYPE_UW);
emit_cmp(BRW_CONDITIONAL_GE, x, dst_x0);
emit_cmp(BRW_CONDITIONAL_GE, y, dst_y0)->predicate = BRW_PREDICATE_NORMAL;
emit_cmp(BRW_CONDITIONAL_L, x, dst_x1)->predicate = BRW_PREDICATE_NORMAL;
emit_cmp(BRW_CONDITIONAL_L, y, dst_y1)->predicate = BRW_PREDICATE_NORMAL;
fs_inst *inst = new (mem_ctx) fs_inst(BRW_OPCODE_AND, 16, g1, f0, g1);
inst->force_writemask_all = true;
insts.push_tail(inst);
}
void bpf_jit_compile(struct bpf_prog *fp)
{
unsigned int cleanup_addr, proglen, oldproglen = 0;
u32 temp[8], *prog, *func, seen = 0, pass;
const struct sock_filter *filter = fp->insns;
int i, flen = fp->len, pc_ret0 = -1;
unsigned int *addrs;
void *image;
if (!bpf_jit_enable)
return;
addrs = kmalloc_array(flen, sizeof(*addrs), GFP_KERNEL);
if (addrs == NULL)
return;
/* Before first pass, make a rough estimation of addrs[]
* each bpf instruction is translated to less than 64 bytes
*/
for (proglen = 0, i = 0; i < flen; i++) {
proglen += 64;
addrs[i] = proglen;
}
cleanup_addr = proglen; /* epilogue address */
image = NULL;
for (pass = 0; pass < 10; pass++) {
u8 seen_or_pass0 = (pass == 0) ? (SEEN_XREG | SEEN_DATAREF | SEEN_MEM) : seen;
/* no prologue/epilogue for trivial filters (RET something) */
proglen = 0;
prog = temp;
/* Prologue */
if (seen_or_pass0) {
if (seen_or_pass0 & SEEN_MEM) {
unsigned int sz = BASE_STACKFRAME;
sz += BPF_MEMWORDS * sizeof(u32);
emit_alloc_stack(sz);
}
/* Make sure we dont leek kernel memory. */
if (seen_or_pass0 & SEEN_XREG)
emit_clear(r_X);
/* If this filter needs to access skb data,
* load %o4 and %o5 with:
* %o4 = skb->len - skb->data_len
* %o5 = skb->data
* And also back up %o7 into r_saved_O7 so we can
* invoke the stubs using 'call'.
*/
if (seen_or_pass0 & SEEN_DATAREF) {
emit_load32(r_SKB, struct sk_buff, len, r_HEADLEN);
emit_load32(r_SKB, struct sk_buff, data_len, r_TMP);
emit_sub(r_HEADLEN, r_TMP, r_HEADLEN);
emit_loadptr(r_SKB, struct sk_buff, data, r_SKB_DATA);
}
}
emit_reg_move(O7, r_saved_O7);
/* Make sure we dont leak kernel information to the user. */
if (bpf_needs_clear_a(&filter[0]))
emit_clear(r_A); /* A = 0 */
for (i = 0; i < flen; i++) {
unsigned int K = filter[i].k;
unsigned int t_offset;
unsigned int f_offset;
u32 t_op, f_op;
u16 code = bpf_anc_helper(&filter[i]);
int ilen;
switch (code) {
case BPF_ALU | BPF_ADD | BPF_X: /* A += X; */
emit_alu_X(ADD);
break;
case BPF_ALU | BPF_ADD | BPF_K: /* A += K; */
emit_alu_K(ADD, K);
break;
case BPF_ALU | BPF_SUB | BPF_X: /* A -= X; */
emit_alu_X(SUB);
break;
case BPF_ALU | BPF_SUB | BPF_K: /* A -= K */
emit_alu_K(SUB, K);
break;
case BPF_ALU | BPF_AND | BPF_X: /* A &= X */
emit_alu_X(AND);
break;
case BPF_ALU | BPF_AND | BPF_K: /* A &= K */
emit_alu_K(AND, K);
break;
case BPF_ALU | BPF_OR | BPF_X: /* A |= X */
emit_alu_X(OR);
break;
case BPF_ALU | BPF_OR | BPF_K: /* A |= K */
emit_alu_K(OR, K);
break;
case BPF_ANC | SKF_AD_ALU_XOR_X: /* A ^= X; */
case BPF_ALU | BPF_XOR | BPF_X:
emit_alu_X(XOR);
break;
case BPF_ALU | BPF_XOR | BPF_K: /* A ^= K */
emit_alu_K(XOR, K);
break;
case BPF_ALU | BPF_LSH | BPF_X: /* A <<= X */
emit_alu_X(SLL);
break;
case BPF_ALU | BPF_LSH | BPF_K: /* A <<= K */
emit_alu_K(SLL, K);
break;
case BPF_ALU | BPF_RSH | BPF_X: /* A >>= X */
emit_alu_X(SRL);
break;
case BPF_ALU | BPF_RSH | BPF_K: /* A >>= K */
emit_alu_K(SRL, K);
break;
case BPF_ALU | BPF_MUL | BPF_X: /* A *= X; */
emit_alu_X(MUL);
break;
case BPF_ALU | BPF_MUL | BPF_K: /* A *= K */
emit_alu_K(MUL, K);
break;
case BPF_ALU | BPF_DIV | BPF_K: /* A /= K with K != 0*/
if (K == 1)
break;
emit_write_y(G0);
/* The Sparc v8 architecture requires
* three instructions between a %y
* register write and the first use.
*/
emit_nop();
emit_nop();
emit_nop();
emit_alu_K(DIV, K);
break;
case BPF_ALU | BPF_DIV | BPF_X: /* A /= X; */
emit_cmpi(r_X, 0);
if (pc_ret0 > 0) {
t_offset = addrs[pc_ret0 - 1];
emit_branch(BE, t_offset + 20);
emit_nop(); /* delay slot */
} else {
emit_branch_off(BNE, 16);
emit_nop();
emit_jump(cleanup_addr + 20);
emit_clear(r_A);
}
emit_write_y(G0);
/* The Sparc v8 architecture requires
* three instructions between a %y
* register write and the first use.
*/
emit_nop();
emit_nop();
emit_nop();
emit_alu_X(DIV);
break;
case BPF_ALU | BPF_NEG:
emit_neg();
break;
case BPF_RET | BPF_K:
if (!K) {
if (pc_ret0 == -1)
pc_ret0 = i;
emit_clear(r_A);
} else {
emit_loadimm(K, r_A);
}
/* Fallthrough */
case BPF_RET | BPF_A:
if (seen_or_pass0) {
if (i != flen - 1) {
emit_jump(cleanup_addr);
emit_nop();
break;
}
if (seen_or_pass0 & SEEN_MEM) {
unsigned int sz = BASE_STACKFRAME;
sz += BPF_MEMWORDS * sizeof(u32);
emit_release_stack(sz);
}
}
/* jmpl %r_saved_O7 + 8, %g0 */
emit_jmpl(r_saved_O7, 8, G0);
emit_reg_move(r_A, O0); /* delay slot */
break;
case BPF_MISC | BPF_TAX:
seen |= SEEN_XREG;
emit_reg_move(r_A, r_X);
break;
case BPF_MISC | BPF_TXA:
seen |= SEEN_XREG;
emit_reg_move(r_X, r_A);
break;
case BPF_ANC | SKF_AD_CPU:
emit_load_cpu(r_A);
break;
case BPF_ANC | SKF_AD_PROTOCOL:
emit_skb_load16(protocol, r_A);
break;
case BPF_ANC | SKF_AD_PKTTYPE:
__emit_skb_load8(__pkt_type_offset, r_A);
emit_andi(r_A, PKT_TYPE_MAX, r_A);
emit_alu_K(SRL, 5);
break;
case BPF_ANC | SKF_AD_IFINDEX:
emit_skb_loadptr(dev, r_A);
emit_cmpi(r_A, 0);
emit_branch(BE_PTR, cleanup_addr + 4);
emit_nop();
emit_load32(r_A, struct net_device, ifindex, r_A);
break;
case BPF_ANC | SKF_AD_MARK:
emit_skb_load32(mark, r_A);
break;
case BPF_ANC | SKF_AD_QUEUE:
emit_skb_load16(queue_mapping, r_A);
break;
case BPF_ANC | SKF_AD_HATYPE:
emit_skb_loadptr(dev, r_A);
emit_cmpi(r_A, 0);
emit_branch(BE_PTR, cleanup_addr + 4);
emit_nop();
emit_load16(r_A, struct net_device, type, r_A);
break;
case BPF_ANC | SKF_AD_RXHASH:
emit_skb_load32(hash, r_A);
break;
case BPF_ANC | SKF_AD_VLAN_TAG:
emit_skb_load16(vlan_tci, r_A);
break;
case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT:
__emit_skb_load8(__pkt_vlan_present_offset, r_A);
if (PKT_VLAN_PRESENT_BIT)
emit_alu_K(SRL, PKT_VLAN_PRESENT_BIT);
if (PKT_VLAN_PRESENT_BIT < 7)
emit_andi(r_A, 1, r_A);
break;
case BPF_LD | BPF_W | BPF_LEN:
emit_skb_load32(len, r_A);
break;
case BPF_LDX | BPF_W | BPF_LEN:
emit_skb_load32(len, r_X);
break;
case BPF_LD | BPF_IMM:
emit_loadimm(K, r_A);
break;
case BPF_LDX | BPF_IMM:
emit_loadimm(K, r_X);
break;
case BPF_LD | BPF_MEM:
seen |= SEEN_MEM;
emit_ldmem(K * 4, r_A);
break;
case BPF_LDX | BPF_MEM:
seen |= SEEN_MEM | SEEN_XREG;
emit_ldmem(K * 4, r_X);
break;
case BPF_ST:
seen |= SEEN_MEM;
emit_stmem(K * 4, r_A);
break;
case BPF_STX:
seen |= SEEN_MEM | SEEN_XREG;
emit_stmem(K * 4, r_X);
break;
#define CHOOSE_LOAD_FUNC(K, func) \
((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset)
case BPF_LD | BPF_W | BPF_ABS:
func = CHOOSE_LOAD_FUNC(K, bpf_jit_load_word);
common_load: seen |= SEEN_DATAREF;
emit_loadimm(K, r_OFF);
emit_call(func);
break;
case BPF_LD | BPF_H | BPF_ABS:
func = CHOOSE_LOAD_FUNC(K, bpf_jit_load_half);
goto common_load;
case BPF_LD | BPF_B | BPF_ABS:
func = CHOOSE_LOAD_FUNC(K, bpf_jit_load_byte);
goto common_load;
case BPF_LDX | BPF_B | BPF_MSH:
func = CHOOSE_LOAD_FUNC(K, bpf_jit_load_byte_msh);
goto common_load;
case BPF_LD | BPF_W | BPF_IND:
func = bpf_jit_load_word;
common_load_ind: seen |= SEEN_DATAREF | SEEN_XREG;
if (K) {
if (is_simm13(K)) {
emit_addi(r_X, K, r_OFF);
} else {
emit_loadimm(K, r_TMP);
emit_add(r_X, r_TMP, r_OFF);
}
} else {
emit_reg_move(r_X, r_OFF);
}
emit_call(func);
break;
case BPF_LD | BPF_H | BPF_IND:
func = bpf_jit_load_half;
goto common_load_ind;
case BPF_LD | BPF_B | BPF_IND:
func = bpf_jit_load_byte;
goto common_load_ind;
case BPF_JMP | BPF_JA:
emit_jump(addrs[i + K]);
emit_nop();
break;
#define COND_SEL(CODE, TOP, FOP) \
case CODE: \
t_op = TOP; \
f_op = FOP; \
goto cond_branch
COND_SEL(BPF_JMP | BPF_JGT | BPF_K, BGU, BLEU);
COND_SEL(BPF_JMP | BPF_JGE | BPF_K, BGEU, BLU);
COND_SEL(BPF_JMP | BPF_JEQ | BPF_K, BE, BNE);
COND_SEL(BPF_JMP | BPF_JSET | BPF_K, BNE, BE);
COND_SEL(BPF_JMP | BPF_JGT | BPF_X, BGU, BLEU);
COND_SEL(BPF_JMP | BPF_JGE | BPF_X, BGEU, BLU);
COND_SEL(BPF_JMP | BPF_JEQ | BPF_X, BE, BNE);
COND_SEL(BPF_JMP | BPF_JSET | BPF_X, BNE, BE);
cond_branch: f_offset = addrs[i + filter[i].jf];
t_offset = addrs[i + filter[i].jt];
/* same targets, can avoid doing the test :) */
if (filter[i].jt == filter[i].jf) {
emit_jump(t_offset);
emit_nop();
break;
}
switch (code) {
case BPF_JMP | BPF_JGT | BPF_X:
case BPF_JMP | BPF_JGE | BPF_X:
case BPF_JMP | BPF_JEQ | BPF_X:
seen |= SEEN_XREG;
emit_cmp(r_A, r_X);
break;
case BPF_JMP | BPF_JSET | BPF_X:
seen |= SEEN_XREG;
emit_btst(r_A, r_X);
break;
case BPF_JMP | BPF_JEQ | BPF_K:
case BPF_JMP | BPF_JGT | BPF_K:
case BPF_JMP | BPF_JGE | BPF_K:
if (is_simm13(K)) {
emit_cmpi(r_A, K);
} else {
emit_loadimm(K, r_TMP);
emit_cmp(r_A, r_TMP);
}
break;
case BPF_JMP | BPF_JSET | BPF_K:
if (is_simm13(K)) {
emit_btsti(r_A, K);
} else {
emit_loadimm(K, r_TMP);
emit_btst(r_A, r_TMP);
}
break;
}
if (filter[i].jt != 0) {
if (filter[i].jf)
t_offset += 8;
emit_branch(t_op, t_offset);
emit_nop(); /* delay slot */
if (filter[i].jf) {
emit_jump(f_offset);
emit_nop();
}
break;
}
emit_branch(f_op, f_offset);
emit_nop(); /* delay slot */
break;
default:
/* hmm, too complex filter, give up with jit compiler */
goto out;
}
ilen = (void *) prog - (void *) temp;
if (image) {
if (unlikely(proglen + ilen > oldproglen)) {
pr_err("bpb_jit_compile fatal error\n");
kfree(addrs);
module_memfree(image);
return;
}
memcpy(image + proglen, temp, ilen);
}
proglen += ilen;
addrs[i] = proglen;
prog = temp;
}
/* last bpf instruction is always a RET :
* use it to give the cleanup instruction(s) addr
*/
cleanup_addr = proglen - 8; /* jmpl; mov r_A,%o0; */
if (seen_or_pass0 & SEEN_MEM)
cleanup_addr -= 4; /* add %sp, X, %sp; */
if (image) {
if (proglen != oldproglen)
pr_err("bpb_jit_compile proglen=%u != oldproglen=%u\n",
proglen, oldproglen);
break;
}
if (proglen == oldproglen) {
image = module_alloc(proglen);
if (!image)
goto out;
}
oldproglen = proglen;
}
if (bpf_jit_enable > 1)
bpf_jit_dump(flen, proglen, pass + 1, image);
if (image) {
fp->bpf_func = (void *)image;
fp->jited = 1;
}
out:
kfree(addrs);
return;
}
/* Emit the fragment program instructions here.
*/
void brw_wm_emit( struct brw_wm_compile *c )
{
struct brw_compile *p = &c->func;
struct intel_context *intel = &p->brw->intel;
GLuint insn;
brw_set_compression_control(p, BRW_COMPRESSION_COMPRESSED);
if (intel->gen >= 6)
brw_set_acc_write_control(p, 1);
/* Check if any of the payload regs need to be spilled:
*/
spill_values(c, c->payload.depth, 4);
spill_values(c, c->creg, c->nr_creg);
spill_values(c, c->payload.input_interp, FRAG_ATTRIB_MAX);
for (insn = 0; insn < c->nr_insns; insn++) {
struct brw_wm_instruction *inst = &c->instruction[insn];
struct brw_reg args[3][4], dst[4];
GLuint i, dst_flags;
/* Get argument regs:
*/
for (i = 0; i < 3; i++)
get_argument_regs(c, inst->src[i], args[i]);
/* Get dest regs:
*/
for (i = 0; i < 4; i++)
if (inst->dst[i])
dst[i] = inst->dst[i]->hw_reg;
else
dst[i] = brw_null_reg();
/* Flags
*/
dst_flags = inst->writemask;
if (inst->saturate)
dst_flags |= SATURATE;
switch (inst->opcode) {
/* Generated instructions for calculating triangle interpolants:
*/
case WM_PIXELXY:
emit_pixel_xy(c, dst, dst_flags);
break;
case WM_DELTAXY:
emit_delta_xy(p, dst, dst_flags, args[0]);
break;
case WM_WPOSXY:
emit_wpos_xy(c, dst, dst_flags, args[0]);
break;
case WM_PIXELW:
emit_pixel_w(c, dst, dst_flags, args[0], args[1]);
break;
case WM_LINTERP:
emit_linterp(p, dst, dst_flags, args[0], args[1]);
break;
case WM_PINTERP:
emit_pinterp(p, dst, dst_flags, args[0], args[1], args[2]);
break;
case WM_CINTERP:
emit_cinterp(p, dst, dst_flags, args[0]);
break;
case WM_FB_WRITE:
emit_fb_write(c, args[0], args[1], args[2], inst->target, inst->eot);
break;
case WM_FRONTFACING:
emit_frontfacing(p, dst, dst_flags);
break;
/* Straightforward arithmetic:
*/
case OPCODE_ADD:
emit_alu2(p, brw_ADD, dst, dst_flags, args[0], args[1]);
break;
case OPCODE_FRC:
emit_alu1(p, brw_FRC, dst, dst_flags, args[0]);
break;
case OPCODE_FLR:
emit_alu1(p, brw_RNDD, dst, dst_flags, args[0]);
break;
case OPCODE_DDX:
emit_ddxy(p, dst, dst_flags, true, args[0]);
break;
case OPCODE_DDY:
emit_ddxy(p, dst, dst_flags, false, args[0]);
break;
case OPCODE_DP2:
emit_dp2(p, dst, dst_flags, args[0], args[1]);
break;
case OPCODE_DP3:
emit_dp3(p, dst, dst_flags, args[0], args[1]);
break;
case OPCODE_DP4:
emit_dp4(p, dst, dst_flags, args[0], args[1]);
break;
case OPCODE_DPH:
emit_dph(p, dst, dst_flags, args[0], args[1]);
break;
case OPCODE_TRUNC:
for (i = 0; i < 4; i++) {
if (dst_flags & (1<<i)) {
brw_RNDZ(p, dst[i], args[0][i]);
}
}
break;
case OPCODE_LRP:
emit_lrp(p, dst, dst_flags, args[0], args[1], args[2]);
break;
case OPCODE_MAD:
emit_mad(p, dst, dst_flags, args[0], args[1], args[2]);
break;
case OPCODE_MOV:
case OPCODE_SWZ:
emit_alu1(p, brw_MOV, dst, dst_flags, args[0]);
break;
case OPCODE_MUL:
emit_alu2(p, brw_MUL, dst, dst_flags, args[0], args[1]);
break;
case OPCODE_XPD:
emit_xpd(p, dst, dst_flags, args[0], args[1]);
break;
/* Higher math functions:
*/
case OPCODE_RCP:
emit_math1(c, BRW_MATH_FUNCTION_INV, dst, dst_flags, args[0]);
break;
case OPCODE_RSQ:
emit_math1(c, BRW_MATH_FUNCTION_RSQ, dst, dst_flags, args[0]);
break;
case OPCODE_SIN:
emit_math1(c, BRW_MATH_FUNCTION_SIN, dst, dst_flags, args[0]);
break;
case OPCODE_COS:
emit_math1(c, BRW_MATH_FUNCTION_COS, dst, dst_flags, args[0]);
break;
case OPCODE_EX2:
emit_math1(c, BRW_MATH_FUNCTION_EXP, dst, dst_flags, args[0]);
break;
case OPCODE_LG2:
emit_math1(c, BRW_MATH_FUNCTION_LOG, dst, dst_flags, args[0]);
break;
case OPCODE_SCS:
/* There is an scs math function, but it would need some
* fixup for 16-element execution.
*/
if (dst_flags & WRITEMASK_X)
emit_math1(c, BRW_MATH_FUNCTION_COS, dst, (dst_flags&SATURATE)|WRITEMASK_X, args[0]);
if (dst_flags & WRITEMASK_Y)
emit_math1(c, BRW_MATH_FUNCTION_SIN, dst+1, (dst_flags&SATURATE)|WRITEMASK_X, args[0]);
break;
case OPCODE_POW:
emit_math2(c, BRW_MATH_FUNCTION_POW, dst, dst_flags, args[0], args[1]);
break;
/* Comparisons:
*/
case OPCODE_CMP:
emit_cmp(p, dst, dst_flags, args[0], args[1], args[2]);
break;
case OPCODE_MAX:
emit_max(p, dst, dst_flags, args[0], args[1]);
break;
case OPCODE_MIN:
emit_min(p, dst, dst_flags, args[0], args[1]);
break;
case OPCODE_SLT:
emit_slt(p, dst, dst_flags, args[0], args[1]);
break;
case OPCODE_SLE:
emit_sle(p, dst, dst_flags, args[0], args[1]);
break;
case OPCODE_SGT:
emit_sgt(p, dst, dst_flags, args[0], args[1]);
break;
case OPCODE_SGE:
emit_sge(p, dst, dst_flags, args[0], args[1]);
break;
case OPCODE_SEQ:
emit_seq(p, dst, dst_flags, args[0], args[1]);
break;
case OPCODE_SNE:
emit_sne(p, dst, dst_flags, args[0], args[1]);
break;
case OPCODE_SSG:
emit_sign(p, dst, dst_flags, args[0]);
break;
case OPCODE_LIT:
emit_lit(c, dst, dst_flags, args[0]);
break;
/* Texturing operations:
*/
case OPCODE_TEX:
emit_tex(c, dst, dst_flags, args[0], c->payload.depth[0].hw_reg,
inst->tex_idx, inst->tex_unit,
inst->tex_shadow);
break;
case OPCODE_TXB:
emit_txb(c, dst, dst_flags, args[0], c->payload.depth[0].hw_reg,
inst->tex_idx, inst->tex_unit);
break;
case OPCODE_KIL:
emit_kil(c, args[0]);
break;
default:
printf("Unsupported opcode %i (%s) in fragment shader\n",
inst->opcode, inst->opcode < MAX_OPCODE ?
_mesa_opcode_string(inst->opcode) :
"unknown");
}
for (i = 0; i < 4; i++)
if (inst->dst[i] && inst->dst[i]->spill_slot)
emit_spill(c,
inst->dst[i]->hw_reg,
inst->dst[i]->spill_slot);
}
/* Only properly tested on ILK */
if (p->brw->intel.gen == 5) {
brw_remove_duplicate_mrf_moves(p);
if (c->dispatch_width == 16)
brw_remove_grf_to_mrf_moves(p);
}
if (unlikely(INTEL_DEBUG & DEBUG_WM)) {
int i;
printf("wm-native:\n");
for (i = 0; i < p->nr_insn; i++)
brw_disasm(stdout, &p->store[i], p->brw->intel.gen);
printf("\n");
}
}
brw_blorp_eu_emitter::brw_blorp_eu_emitter(struct brw_context *brw)
: brw_ctx (brw), mem_ctx(ralloc_context(NULL)), c(rzalloc(mem_ctx, struct brw_wm_compile)),
generator(brw, c, NULL, NULL, false)
{
}
brw_blorp_eu_emitter::~brw_blorp_eu_emitter()
{
ralloc_free(mem_ctx);
}
const unsigned *
brw_blorp_eu_emitter::get_program(unsigned *program_size, FILE *dump_file)
{
const unsigned *res;
if (unlikely(INTEL_DEBUG & DEBUG_BLORP)) {
fprintf(stderr, "Native code for BLORP blit:\n");
res = generator.generate_assembly(NULL, &insts, program_size, dump_file);
fprintf(stderr, "\n");
} else {
res = generator.generate_assembly(NULL, &insts, program_size);
}
return res;
}
/**
* Emit code that kills pixels whose X and Y coordinates are outside the
* boundary of the rectangle defined by the push constants (dst_x0, dst_y0,
* dst_x1, dst_y1).
*/
void
brw_blorp_eu_emitter::emit_kill_if_outside_rect(const struct brw_reg &x,
const struct brw_reg &y,
const struct brw_reg &dst_x0,
const struct brw_reg &dst_x1,
const struct brw_reg &dst_y0,
const struct brw_reg &dst_y1)
{
struct brw_reg f0 = brw_flag_reg(0, 0);
struct brw_reg g1 = retype(brw_vec1_grf(1, 7), BRW_REGISTER_TYPE_UW);
emit_cmp(BRW_CONDITIONAL_GE, x, dst_x0);
emit_cmp(BRW_CONDITIONAL_GE, y, dst_y0)->predicate = BRW_PREDICATE_NORMAL;
emit_cmp(BRW_CONDITIONAL_L, x, dst_x1)->predicate = BRW_PREDICATE_NORMAL;
emit_cmp(BRW_CONDITIONAL_L, y, dst_y1)->predicate = BRW_PREDICATE_NORMAL;
fs_inst *inst = new (mem_ctx) fs_inst(BRW_OPCODE_AND, g1, f0, g1);
inst->force_writemask_all = true;
insts.push_tail(inst);
}
void
brw_blorp_eu_emitter::emit_texture_lookup(const struct brw_reg &dst,
enum opcode op,
unsigned base_mrf,
unsigned msg_length)
{
fs_inst *inst = new (mem_ctx) fs_inst(op, dst, brw_message_reg(base_mrf));
inst->base_mrf = base_mrf;
inst->mlen = msg_length;
inst->sampler = 0;
inst->header_present = false;
insts.push_tail(inst);
}
/* Emit the fragment program instructions here.
*/
void brw_wm_emit( struct brw_wm_compile *c )
{
struct brw_compile *p = &c->func;
GLuint insn;
brw_set_compression_control(p, BRW_COMPRESSION_COMPRESSED);
/* Check if any of the payload regs need to be spilled:
*/
spill_values(c, c->payload.depth, 4);
spill_values(c, c->creg, c->nr_creg);
spill_values(c, c->payload.input_interp, FRAG_ATTRIB_MAX);
for (insn = 0; insn < c->nr_insns; insn++) {
struct brw_wm_instruction *inst = &c->instruction[insn];
struct brw_reg args[3][4], dst[4];
GLuint i, dst_flags;
/* Get argument regs:
*/
for (i = 0; i < 3; i++)
get_argument_regs(c, inst->src[i], args[i]);
/* Get dest regs:
*/
for (i = 0; i < 4; i++)
if (inst->dst[i])
dst[i] = inst->dst[i]->hw_reg;
else
dst[i] = brw_null_reg();
/* Flags
*/
dst_flags = inst->writemask;
if (inst->saturate)
dst_flags |= SATURATE;
switch (inst->opcode) {
/* Generated instructions for calculating triangle interpolants:
*/
case WM_PIXELXY:
emit_pixel_xy(p, dst, dst_flags, args[0]);
break;
case WM_DELTAXY:
emit_delta_xy(p, dst, dst_flags, args[0], args[1]);
break;
case WM_WPOSXY:
emit_wpos_xy(c, dst, dst_flags, args[0]);
break;
case WM_PIXELW:
emit_pixel_w(p, dst, dst_flags, args[0], args[1]);
break;
case WM_LINTERP:
emit_linterp(p, dst, dst_flags, args[0], args[1]);
break;
case WM_PINTERP:
emit_pinterp(p, dst, dst_flags, args[0], args[1], args[2]);
break;
case WM_CINTERP:
emit_cinterp(p, dst, dst_flags, args[0]);
break;
case WM_FB_WRITE:
emit_fb_write(c, args[0], args[1], args[2], inst->target, inst->eot);
break;
/* Straightforward arithmetic:
*/
case OPCODE_ADD:
emit_alu2(p, brw_ADD, dst, dst_flags, args[0], args[1]);
break;
case OPCODE_FRC:
emit_alu1(p, brw_FRC, dst, dst_flags, args[0]);
break;
case OPCODE_FLR:
emit_alu1(p, brw_RNDD, dst, dst_flags, args[0]);
break;
case OPCODE_DP3: /* */
emit_dp3(p, dst, dst_flags, args[0], args[1]);
break;
case OPCODE_DP4:
emit_dp4(p, dst, dst_flags, args[0], args[1]);
break;
case OPCODE_DPH:
emit_dph(p, dst, dst_flags, args[0], args[1]);
break;
case OPCODE_LRP: /* */
emit_lrp(p, dst, dst_flags, args[0], args[1], args[2]);
break;
case OPCODE_MAD:
emit_mad(p, dst, dst_flags, args[0], args[1], args[2]);
break;
case OPCODE_MOV:
case OPCODE_SWZ:
emit_alu1(p, brw_MOV, dst, dst_flags, args[0]);
break;
case OPCODE_MUL:
emit_alu2(p, brw_MUL, dst, dst_flags, args[0], args[1]);
break;
case OPCODE_XPD:
emit_xpd(p, dst, dst_flags, args[0], args[1]);
break;
/* Higher math functions:
*/
case OPCODE_RCP:
emit_math1(p, BRW_MATH_FUNCTION_INV, dst, dst_flags, args[0]);
break;
case OPCODE_RSQ:
emit_math1(p, BRW_MATH_FUNCTION_RSQ, dst, dst_flags, args[0]);
break;
case OPCODE_SIN:
emit_math1(p, BRW_MATH_FUNCTION_SIN, dst, dst_flags, args[0]);
break;
case OPCODE_COS:
emit_math1(p, BRW_MATH_FUNCTION_COS, dst, dst_flags, args[0]);
break;
case OPCODE_EX2:
emit_math1(p, BRW_MATH_FUNCTION_EXP, dst, dst_flags, args[0]);
break;
case OPCODE_LG2:
emit_math1(p, BRW_MATH_FUNCTION_LOG, dst, dst_flags, args[0]);
break;
case OPCODE_SCS:
/* There is an scs math function, but it would need some
* fixup for 16-element execution.
*/
if (dst_flags & WRITEMASK_X)
emit_math1(p, BRW_MATH_FUNCTION_COS, dst, (dst_flags&SATURATE)|WRITEMASK_X, args[0]);
if (dst_flags & WRITEMASK_Y)
emit_math1(p, BRW_MATH_FUNCTION_SIN, dst+1, (dst_flags&SATURATE)|WRITEMASK_X, args[0]);
break;
case OPCODE_POW:
emit_math2(p, BRW_MATH_FUNCTION_POW, dst, dst_flags, args[0], args[1]);
break;
/* Comparisons:
*/
case OPCODE_CMP:
emit_cmp(p, dst, dst_flags, args[0], args[1], args[2]);
break;
case OPCODE_MAX:
emit_max(p, dst, dst_flags, args[0], args[1]);
break;
case OPCODE_MIN:
emit_min(p, dst, dst_flags, args[0], args[1]);
break;
case OPCODE_SLT:
emit_slt(p, dst, dst_flags, args[0], args[1]);
break;
case OPCODE_SLE:
emit_sle(p, dst, dst_flags, args[0], args[1]);
break;
case OPCODE_SGT:
emit_sgt(p, dst, dst_flags, args[0], args[1]);
break;
case OPCODE_SGE:
emit_sge(p, dst, dst_flags, args[0], args[1]);
break;
case OPCODE_SEQ:
emit_seq(p, dst, dst_flags, args[0], args[1]);
break;
case OPCODE_SNE:
emit_sne(p, dst, dst_flags, args[0], args[1]);
break;
case OPCODE_LIT:
emit_lit(p, dst, dst_flags, args[0]);
break;
/* Texturing operations:
*/
case OPCODE_TEX:
emit_tex(c, inst, dst, dst_flags, args[0]);
break;
case OPCODE_TXB:
emit_txb(c, inst, dst, dst_flags, args[0]);
break;
case OPCODE_KIL:
emit_kil(c, args[0]);
break;
default:
_mesa_printf("unsupport opcode %d in fragment program\n",
inst->opcode);
}
for (i = 0; i < 4; i++)
if (inst->dst[i] && inst->dst[i]->spill_slot)
emit_spill(c,
inst->dst[i]->hw_reg,
inst->dst[i]->spill_slot);
}
}
